• KIEE International Transactions on Power Engineering
• /
• v.2A no.4
• /
• pp.136-144
• /
• 2002

Load models are very important for improving the accuracy of stability analysis and load flow studies. Various loads are connected to a power bus and their characteristics of power consumption change with voltage and frequency. Thus, the effect of voltage/frequency changes must be considered in load modeling. In this work, artificial neural networks-ANNs- were used to construct the component load models for more accurate modeling. A typical residential load was selected and subjected to a test under variable voltage/frequency conditions. Acquired data were used to construct component models by ANNs. The aggregation process of separately determined load models is also presented in the paper. Furthermore, this paper proposes a method to transform a single load model constructed by the aggregation method into a mathematical load model that can be used in traditional power system analysis software.

• Proceedings of the KIEE Conference
• /
• 1997.07b
• /
• pp.485-487
• /
• 1997

Schemes for detecting and diagnosing faults are presented. Faults are detected when residuals change significantly and thresholds are exceed. Two stage artificial neural networks are applied to diagnose faults. The idealized steady state patterns of residuals are defined and learned by ANNs using back propagation algorithm. The first stage ANN is trained to classify the subsystem in which the various faults are located. The first stage ANN could be also used to detect faults with threshold, checking. The second stage ANNs are trained to discriminate the specific cause of a fault at the subsystem level.

• Bulletin of the Korean Chemical Society
• /
• v.28 no.9
• /
• pp.1477-1484
• /
• 2007

Artificial neural networks (ANNs), for a first time, were successfully developed for the prediction partial molar heat capacity of aqueous solutions at infinite dilution for various polar aromatic compounds over wide range of temperatures (303.55-623.20 K) and pressures (0.1-30.2 MPa). Two three-layered feed forward ANNs with back-propagation of error were generated using three (the heat capacity in T = 303.55 K and P = 0.1 MPa, temperature and pressure) and six parameters (four theoretical descriptors, temperature and pressure) as inputs and its output is partial molar heat capacity at infinite dilution. It was found that properly selected and trained neural networks could fairly represent dependence of the heat capacity on the molecular descriptors, temperature and pressure. Mean percentage deviations (MPD) for prediction set by the models are 4.755 and 4.642, respectively.

• Proceedings of the KIEE Conference
• /
• 2004.11b
• /
• pp.91-93
• /
• 2004

Load forecasting is essential in order to supply electrical energy stably and economically in power systems. ANNs have flexibility to predict a nonlinear feature of load profiles. In this paper, we selected just the necessary input variables used in the paper(2) which is based on the phase-space embedding of a load time-series and reviewing others. So only 5 input variables were selected to forecast for spring, fall and winter season and another input considering temperature sensitivity is added during the summer season. The training cases are also selected from all previous data composed training cases of a 7-day, 14-day and 30-day period. Finally, we selected the training case of a 7-day period because it can be used in STLF without sacrificing the accuracy of the forecast. This allows more compact ANNs, smaller training cases. Consequently, test results show that compact neural networks can be forecasted without sacrificing the accuracy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.159-159
• /
• 2019

In this study, the simulation of sediment deposition at Sangju weir reservoir, South Korea, was carried out using artificial neural networks. The ANNs have typically been used in water resources engineering problems for their robustness and high degree of accuracy. Three basic variables namely turbid water inflow, outflow, and water stage have been used as input variables. It was found that ANNs were able to establish valid relationship between input variables and target variable of sedimentation. The R value was 0.9806, 0.9091, and 0.8758 for training, validation, and testing phase respectively. Comparative analysis was also performed to find optimum structure of ANN for sediment deposition prediction. 3-14-1 network architecture using BR algorithm outperformed all other combinations. It was concluded that ANN possess mapping capabilities for complex, non-linear phenomenon of reservoir sedimentation.

• Computers and Concrete
• /
• v.24 no.5
• /
• pp.399-412
• /
• 2019

In this investigation, Elman neural networks were utilized for predicting the mechanical properties of Self-Compacting Concretes (SCCs). Elman models were designed by using experimental data of many different concrete mixdesigns of various types of SCC that were collected from the literature. In order to investigate the effectiveness of the selected input variables on the network performance in predicting intended properties, utilized data in artificial neural networks were considered in two sets of 8 and 140 input variables. The obtained outcomes showed that not only can the developed Elman ANNs predict the mechanical properties of SCCs with high accuracy, but also for all of the desired outputs, networks with 140 inputs, compared to ones with 8, have a remarkable percent improvement in the obtained prediction results. The prediction accuracy can significantly be improved by using a more complete and accurate set of key factors affecting the desired outputs, as input variables, in the networks, which is leading to more similarity of the predicted results gained from networks to experimental results.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.16 no.3
• /
• pp.321-339
• /
• 2014

This paper concerns the development of a knowledge-based tunnel design system within the framework of artifical neural networks(ANNs). The system is aimed at expediting a routine tunnel design works such as computation of segment lining body forces and stability analysis of selected cross section. A number of sub-modules for computation of segment lining body forces and stability analysis were developed and implemented to the system. It is shown that the ANNs trained with the results of 3D numerical analyses can be generalized with a reasonable accuracy, and that the ANN based tunnel design concept is a robust tool for tunnel design optimization. The details of the system architecture and the ANNs development are discussed in this paper.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.337-340
• /
• 2004

The exactly reproduced prosody of a TTS system is one of the key factors that affect the naturalness of synthesized speech. In general, rules about prosody had been gathered either from linguistic knowledge or by analyzing the prosodic information from natural speech. But these could not be perfect and some of them could be incorrect. So we proposed artificial neural network(ANN)s that can be trained to team the prosody of natural speech and generate it. In learning phase, let ANNs learn the pitch and energy contour of center phoneme by applying a string of phonemes in a sentence to ANNs and comparing the output pattern with target pattern and making adjustment in weighting values to get the least mean square error between them. In test phase, the estimation rates were computed. We saw that ANNs could generate the prosody of a sentence.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.16 no.1
• /
• pp.13-24
• /
• 2014

This paper presents development of artificial neural network(ANN) based prediction method for section forces of TBM tunnel segment lining in an effort to develop an automatized design technique. A series of design cases were first developed and subsequently analyzed using the two-ring beam finite element model. The results were then used to form a database for use as training and validation data sets for ANN development. Using the database, optimized ANNs were developed that can readily be used to predict maximum sectional forces and their distributions. It is shown that the compute maximum section forces and their distributions by the developed ANNs are almost identical to the computed by the two-ring beam finite element model, implying that the developed ANNs can be used as design tools which expedite routine design calculation process. The results of this study indicate that the neural network model can be effectively used as a reliable and simple predictive tool for the prediction of segment sectional forces for design.

• Journal of Korean Society of Transportation
• /
• v.18 no.4
• /
• pp.75-85
• /
• 2000

The Purpose of this study is to analyze wether the composition of training sample have a relation with the Predictive ability and the learning results of ANNs(Artificial Neural Networks) fur predicting one cycle ahead of the queue length(veh.) in a signalized intersection. In this study, ANNs\` training sample is classified into the assumption of two cases. The first is to utilize time-series(Per cycle) data of queue length which would be detected by one detector (loop or video) The second is to use time-space correlated data(such as: a upstream feed-in flow, a link travel time, a approach maximum stationary queue length, a departure volume) which would be detected by a integrative vehicle detection systems (loop detector, video detector, RFIDs) which would be installed between the upstream node(intersection) and downstream node. The major findings from this paper is In Daechi Intersection(GangNamGu, Seoul), in the case of ANNs\` training sample constructed by time-space correlated data between the upstream node(intersection) and downstream node, the pattern recognition ability of an interrupted traffic flow is better.